{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:5TKOU3UHY5PNSXDWXSQJQKZRWK","short_pith_number":"pith:5TKOU3UH","canonical_record":{"source":{"id":"2206.13852","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2022-06-28T09:33:21Z","cross_cats_sorted":[],"title_canon_sha256":"ce7fd68b373e80660beedbdbc9737cc2c656c2cebece8badfcbbfbd2f6d59a21","abstract_canon_sha256":"c335e3f2a4e3a9a97cb59fdc2f2191dedc2aeeb3b0cc106f71b65a1bfd911996"},"schema_version":"1.0"},"canonical_sha256":"ecd4ea6e87c75ed95c76bca0982b31b2a80639b75f439959e26f830ddb7745fc","source":{"kind":"arxiv","id":"2206.13852","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.13852","created_at":"2026-07-05T05:31:50Z"},{"alias_kind":"arxiv_version","alias_value":"2206.13852v2","created_at":"2026-07-05T05:31:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.13852","created_at":"2026-07-05T05:31:50Z"},{"alias_kind":"pith_short_12","alias_value":"5TKOU3UHY5PN","created_at":"2026-07-05T05:31:50Z"},{"alias_kind":"pith_short_16","alias_value":"5TKOU3UHY5PNSXDW","created_at":"2026-07-05T05:31:50Z"},{"alias_kind":"pith_short_8","alias_value":"5TKOU3UH","created_at":"2026-07-05T05:31:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:5TKOU3UHY5PNSXDWXSQJQKZRWK","target":"record","payload":{"canonical_record":{"source":{"id":"2206.13852","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2022-06-28T09:33:21Z","cross_cats_sorted":[],"title_canon_sha256":"ce7fd68b373e80660beedbdbc9737cc2c656c2cebece8badfcbbfbd2f6d59a21","abstract_canon_sha256":"c335e3f2a4e3a9a97cb59fdc2f2191dedc2aeeb3b0cc106f71b65a1bfd911996"},"schema_version":"1.0"},"canonical_sha256":"ecd4ea6e87c75ed95c76bca0982b31b2a80639b75f439959e26f830ddb7745fc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:31:50.911662Z","signature_b64":"7WKR7FWC+/yaYid+i/6OHcPVBbBy29qF7S3YQ2p70T3lK8jXtoAiMkMOpolpEde/CJhdSUcNIQBF/RXQzhCXCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ecd4ea6e87c75ed95c76bca0982b31b2a80639b75f439959e26f830ddb7745fc","last_reissued_at":"2026-07-05T05:31:50.911215Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:31:50.911215Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2206.13852","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:31:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AWspvpgC/jLKaM3mddFXXl3qNZ9JecF4OyileOzbdaGUy4e5txasUpD5adPAX3MF7VHtSUvA4B/9mMOavMslDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T23:36:59.204424Z"},"content_sha256":"7f0f74a17597cd530361fcb0ad8ef5dcfd5b3822ddd95eb95591efaf6e4d6a7c","schema_version":"1.0","event_id":"sha256:7f0f74a17597cd530361fcb0ad8ef5dcfd5b3822ddd95eb95591efaf6e4d6a7c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:5TKOU3UHY5PNSXDWXSQJQKZRWK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Get Your Memory Right: The Crispy Resource Allocation Assistant for Large-Scale Data Processing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Dominik Scheinert, Jonathan Bader, Jonathan Will, Lauritz Thamsen, Odej Kao","submitted_at":"2022-06-28T09:33:21Z","abstract_excerpt":"Distributed dataflow systems like Apache Spark and Apache Hadoop enable data-parallel processing of large datasets on clusters. Yet, selecting appropriate computational resources for dataflow jobs -- that neither lead to bottlenecks nor to low resource utilization -- is often challenging, even for expert users such as data engineers. Further, existing automated approaches to resource selection rely on the assumption that a job is recurring to learn from previous runs or to warrant the cost of full test runs to learn from. However, this assumption often does not hold since many jobs are too uni"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.13852","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2206.13852/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:31:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q5piixk4WHHGTuh6zEsN5I8BwtFeKQY3xMoGUsumrMqBBz7HFx3O462hEK1g7uCr4RH3p10lCwbjeO+dIRceCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T23:36:59.204925Z"},"content_sha256":"6f680ff86e03d486cfbc7f9966bb99c55bc11b99e772575083590e97cfeda7fb","schema_version":"1.0","event_id":"sha256:6f680ff86e03d486cfbc7f9966bb99c55bc11b99e772575083590e97cfeda7fb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5TKOU3UHY5PNSXDWXSQJQKZRWK/bundle.json","state_url":"https://pith.science/pith/5TKOU3UHY5PNSXDWXSQJQKZRWK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5TKOU3UHY5PNSXDWXSQJQKZRWK/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-23T23:36:59Z","links":{"resolver":"https://pith.science/pith/5TKOU3UHY5PNSXDWXSQJQKZRWK","bundle":"https://pith.science/pith/5TKOU3UHY5PNSXDWXSQJQKZRWK/bundle.json","state":"https://pith.science/pith/5TKOU3UHY5PNSXDWXSQJQKZRWK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5TKOU3UHY5PNSXDWXSQJQKZRWK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:5TKOU3UHY5PNSXDWXSQJQKZRWK","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"c335e3f2a4e3a9a97cb59fdc2f2191dedc2aeeb3b0cc106f71b65a1bfd911996","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2022-06-28T09:33:21Z","title_canon_sha256":"ce7fd68b373e80660beedbdbc9737cc2c656c2cebece8badfcbbfbd2f6d59a21"},"schema_version":"1.0","source":{"id":"2206.13852","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.13852","created_at":"2026-07-05T05:31:50Z"},{"alias_kind":"arxiv_version","alias_value":"2206.13852v2","created_at":"2026-07-05T05:31:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.13852","created_at":"2026-07-05T05:31:50Z"},{"alias_kind":"pith_short_12","alias_value":"5TKOU3UHY5PN","created_at":"2026-07-05T05:31:50Z"},{"alias_kind":"pith_short_16","alias_value":"5TKOU3UHY5PNSXDW","created_at":"2026-07-05T05:31:50Z"},{"alias_kind":"pith_short_8","alias_value":"5TKOU3UH","created_at":"2026-07-05T05:31:50Z"}],"graph_snapshots":[{"event_id":"sha256:6f680ff86e03d486cfbc7f9966bb99c55bc11b99e772575083590e97cfeda7fb","target":"graph","created_at":"2026-07-05T05:31:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2206.13852/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Distributed dataflow systems like Apache Spark and Apache Hadoop enable data-parallel processing of large datasets on clusters. Yet, selecting appropriate computational resources for dataflow jobs -- that neither lead to bottlenecks nor to low resource utilization -- is often challenging, even for expert users such as data engineers. Further, existing automated approaches to resource selection rely on the assumption that a job is recurring to learn from previous runs or to warrant the cost of full test runs to learn from. However, this assumption often does not hold since many jobs are too uni","authors_text":"Dominik Scheinert, Jonathan Bader, Jonathan Will, Lauritz Thamsen, Odej Kao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2022-06-28T09:33:21Z","title":"Get Your Memory Right: The Crispy Resource Allocation Assistant for Large-Scale Data Processing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.13852","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:7f0f74a17597cd530361fcb0ad8ef5dcfd5b3822ddd95eb95591efaf6e4d6a7c","target":"record","created_at":"2026-07-05T05:31:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"c335e3f2a4e3a9a97cb59fdc2f2191dedc2aeeb3b0cc106f71b65a1bfd911996","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2022-06-28T09:33:21Z","title_canon_sha256":"ce7fd68b373e80660beedbdbc9737cc2c656c2cebece8badfcbbfbd2f6d59a21"},"schema_version":"1.0","source":{"id":"2206.13852","kind":"arxiv","version":2}},"canonical_sha256":"ecd4ea6e87c75ed95c76bca0982b31b2a80639b75f439959e26f830ddb7745fc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ecd4ea6e87c75ed95c76bca0982b31b2a80639b75f439959e26f830ddb7745fc","first_computed_at":"2026-07-05T05:31:50.911215Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:31:50.911215Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7WKR7FWC+/yaYid+i/6OHcPVBbBy29qF7S3YQ2p70T3lK8jXtoAiMkMOpolpEde/CJhdSUcNIQBF/RXQzhCXCA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:31:50.911662Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.13852","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7f0f74a17597cd530361fcb0ad8ef5dcfd5b3822ddd95eb95591efaf6e4d6a7c","sha256:6f680ff86e03d486cfbc7f9966bb99c55bc11b99e772575083590e97cfeda7fb"],"state_sha256":"6f2d45f7d78a428148e082d669673b73ef371cb635e7ec6fc1a79e6a8a993427"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"blLArWeTj//dOhKYKfppjN3WFXxx4z/u4/VzG6plJ75JPaRq7QutZcxL7Vez+cmTXTCxWOnUxWgt6P5VKaVdDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T23:36:59.209534Z","bundle_sha256":"adbfc5dd46c85961d3da2d4ad86f6c6c76bf05ff4c3375462ff394a2e29a7d80"}}